Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Yap, Jia Qing
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.16335